import os
import tempfile
import re
import streamlit as st
import docx
import textract

#####################################
# Function: Extract Text from File
#####################################
def extract_text_from_file(file_obj):
    """
    Extract text from .doc and .docx files.
    Returns the extracted text or an error message if extraction fails.
    """
    filename = file_obj.name
    ext = os.path.splitext(filename)[1].lower()
    text = ""

    if ext == ".docx":
        try:
            document = docx.Document(file_obj)
            text = "\n".join([para.text for para in document.paragraphs])
        except Exception as e:
            text = f"Error processing DOCX file: {e}"
    elif ext == ".doc":
        try:
            # textract requires a filename, so create a temporary file.
            with tempfile.NamedTemporaryFile(delete=False, suffix=".doc") as tmp:
                tmp.write(file_obj.read())
                tmp.flush()
                tmp_filename = tmp.name
            text = textract.process(tmp_filename).decode("utf-8")
        except Exception as e:
            text = f"Error processing DOC file: {e}"
        finally:
            try:
                os.remove(tmp_filename)
            except Exception:
                pass
    else:
        text = "Unsupported file type."

    return text

#####################################
# Function: Extract Basic Resume Information
#####################################
def extract_basic_resume_info(text):
    """
    Parse the extracted text to summarize basic info:
    - Name
    - Age
    - Work Experience (e.g., number of years or description)
    - Expected Industry/Direction
    """
    info = {
        "Name": None,
        "Age": None,
        "Work Experience": None,
        "Expected Industry/Direction": None,
    }

    # Try to extract Name (e.g., lines like "Name: John Doe")
    name_match = re.search(r"[Nn]ame[:\-]\s*([A-Za-z\s]+)", text)
    if name_match:
        info["Name"] = name_match.group(1).strip()
    else:
        # Fallback: Look for a potential name (heuristic: two or three capitalized words)
        potential_names = re.findall(r"\b[A-Z][a-z]+(?:\s+[A-Z][a-z]+){1,2}\b", text)
        if potential_names:
            info["Name"] = potential_names[0]

    # Extract Age (assuming a line like "Age: 28")
    age_match = re.search(r"[Aa]ge[:\-]\s*(\d{1,2})", text)
    if age_match:
        info["Age"] = age_match.group(1)

    # Extract Work Experience (e.g., "5 years of experience" or "Experience: 5 years in...")
    exp_match = re.search(r"(\d+)\s+(years|yrs)\s+(?:of\s+)?experience", text, re.IGNORECASE)
    if exp_match:
        info["Work Experience"] = f"{exp_match.group(1)} {exp_match.group(2)}"
    else:
        # Look for a line that has work experience info
        exp_line = re.search(r"(Experience|Background)[:\-]\s*(.*)", text, re.IGNORECASE)
        if exp_line:
            info["Work Experience"] = exp_line.group(2).strip()

    # Extract Expected Industry/Direction 
    # (e.g., "Interest: Software Development" or "Expected Industry: Healthcare")
    industry_match = re.search(r"(Industry|Interest|Direction)[:\-]\s*(.+)", text, re.IGNORECASE)
    if industry_match:
        info["Expected Industry/Direction"] = industry_match.group(2).strip()

    return info

#####################################
# Main Resume Processing Logic
#####################################
def process_resume(file_obj):
    if file_obj is None:
        return None, None
    # Extract text content from the file.
    resume_text = extract_text_from_file(file_obj)
    # Extract summarized basic info from the resume text.
    basic_info = extract_basic_resume_info(resume_text)
    return resume_text, basic_info

#####################################
# Streamlit Interface
#####################################
st.title("Resume Summary App")
st.markdown("""
Upload your resume file (supported formats: **.doc** or **.docx**) to extract and summarize its content.
The basic details, including name, age, work experience, and expected industry, will be displayed along with the full text content.
""")

uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx"])

if st.button("Extract Information"):
    if uploaded_file is None:
        st.error("Please upload a file first.")
    else:
        with st.spinner("Extracting information..."):
            resume_text, resume_info = process_resume(uploaded_file)

        st.subheader("Extracted Resume Text")
        st.text_area("", resume_text, height=300)

        st.subheader("Basic Resume Information")
        st.json(resume_info)